Blog · Coming soon

Writing on memory, agents, and building Hebbrix

A preview of what we're writing. These posts are on the way, not published yet.

Upcoming

Why we modeled memory after the Ebbinghaus forgetting curve

Vector search treats every memory as equal. Human memory doesn't, and neither does ours. A close look at why cognitive science made a better foundation for AI memory than information retrieval theory.

Featured post
"The forgetting curve isn't just a metaphor. It's a precise mathematical description of how useful information decays over time. We built our memory tiers around it."
Coming soon
More posts coming soon
Upcoming
Five layers of retrieval: how Hebbrix's hybrid search actually works

Vector search alone isn't enough. We run five retrieval signals in parallel (semantic, BM25, graph traversal, importance, and recency), and here's how we fuse them into one result.

Soon
Upcoming
Context engineering is replacing prompt engineering

The teams building the best agents have moved past crafting prompts. They're engineering what reaches the model. Here's what that shift actually looks like in practice.

Soon
Upcoming
Building a knowledge graph from natural language, at production scale

How we pull entities and relationships out of unstructured text, link them into a graph, and keep extraction latency sub-second per memory, all without a schema.

Soon
Upcoming
Hebbrix vs Mem0 vs Zep: an honest comparison

We built a test suite that measures retrieval accuracy, latency, and memory quality across four memory systems. Here's what we found, including where we lost.

Soon
Upcoming
Reinforcement learning for memory quality: how we do it without labels

Our six RL quality checks run after every interaction. No thumbs-up buttons, no manual feedback loops. Here's the mechanism behind automatic memory improvement.

Soon
Upcoming
Why we chose a warm brand for an infrastructure company

Memory is the most human thing we're building. Cream paper, ink, and Fraunces type felt more honest than the cyan-on-black alternative. A note on the rebrand.

Soon
Upcoming
From zero to production memory: a walkthrough for LangChain developers

We took a real LangChain agent and added Hebbrix in under 10 minutes. Session transcript, timing data, and the before/after retrieval comparison included.

Soon
Stay updated

New posts, roughly twice a month

Engineering walkthroughs, product updates, and notes on context engineering. Nothing else clogging your inbox.